Electronic Health Records Phenotyping

SSC Annual Meeting 2022 Biostatistics Workshop

Welcome

This website contains materials for Biostatistics Workshop in 2022 SSC Annual Meeting Online.

In this workshop, we will introduce statistical learning methods designed to expedite the phenotyping process in order to improve the scalability of EHR research.

• Module 1 Exploratory Data Analysis (EDA) and Feature Selection (Slides)

Exerciese 1

• Module 2 Model Fitting and Evaluation (Slides)

Exerciese 2

PheCAP

We will use the real EHR data examples from PheCAP package.

The PheCAP is an R package that implements high-throughput phenotyping with electronic health record (EHR) using a common automated pipeline. It contains simulated data and real EHR data examples, with structured data and information extracted from the narrative clinical notes using natural language processing (NLP).

Required packages

Here is a list of packages that will be used during the workshop.

# From CRAN
install.packages("PheCAP")
install.packages("tidyverse")

Resources

• Publicly available EHR dataset

  • Physionet
  • n2n2 competitions

• NLP software

  • cTAKES
  • clinspacy
  • medspacy

Acknowledgments

This website was made with the distill package, drawn mostly from Silvia Canelón’s Sharing Your Work with xaringan.